file1

This brings you to the following dialogue box:
CHAPTER 6 Correlational analysis: Pearson’s r [SWM 5] 183
Move both variables from the left-hand side to the right-hand side. Make sure the Pearson and Onetailed
options are selected. Then click on OK. This will obtain your results.
Let’s look at the output from SPSS. The important results for your write-ups are:
• the correlation coeffi cient r; this shows us how strongly our variables relate to each other, and in
what direction
• the associated probability level, letting us know the likelihood of our correlation coeffi cient arising
by sampling error, assuming the null hypothesis to be true.
Results are given in the form of a matrix. A matrix is simply a set of numbers arranged in rows and
columns. The correlation matrix is an example of a square symmetric matrix. You should fi nd that
each variable correlates perfectly with itself (otherwise something is amiss!). You will also note that
results are given twice: each half of the matrix is a mirror image of itself. This means you have to look
at one half (of the diagonal) only. SPSS also lets us know the number of pairs for each variable. You
can see from the output below that the point where our variable ICECREAM meets our variable TEMP
gives us the information we need. The fi rst line gives us the correlation coeffi cient – it is usual for us
to give this correct to two decimal places. The achieved signifi cance level is given on the second line,
and the third line confi rms how many pairs we have in the analysis. Remember that, when SPSS gives
a row of zeros, change the last zero to a 1 and use the < sign (i.e. p < 0.001, n = 20). Note that our
correlation coeffi cient is positive – as temperature rises, so does the sale of ice-creams.